From 37af68cfd0d30f7eb8cd00996b6120311420bbe0 Mon Sep 17 00:00:00 2001 From: Alexander Miroshnichenko Date: Wed, 27 May 2026 22:06:38 +0300 Subject: [PATCH] docs(AGENTS): add sequential-thinking MCP and caveman skill requirements - Require sequentialthinking MCP for all planning/problem-solving - Add caveman mode for compressed user-facing communication - Clarify karpathy-guidelines usage for task execution quality --- AGENTS.md | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) diff --git a/AGENTS.md b/AGENTS.md index 9b5d4fe..6f4ee40 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -33,6 +33,27 @@ Always use these skills when working with this repository: - **nix-flakes** - For reproducible builds, flake management, and devShell operations - **karpathy-guidelines** - For high-quality task execution best practices +### Required MCP Server + +- **sequentialthinking** — MUST be used for ANY planning, problem-solving, or decision-making. + Invoke `sequentialthinking` MCP before: + - Designing implementation approaches + - Debugging non-obvious issues + - Evaluating trade-offs between approaches + - Breaking down complex tasks + - When you're uncertain about the best path forward + + Do NOT skip deliberative thinking. Surface reasoning through sequentialthinking before acting. + +### Communication: Caveman Mode + +Use **caveman** skill for all user-facing communication. Responses should be: +- Ultra-compressed — cut token waste, keep technical substance +- Direct — no filler, no hedging, no "I'd recommend" +- Action-oriented — state what was done and what's next + +Trigger: `skill: "caveman"` before responding to the user. + ### Blueprint Framework This project uses `numtide/blueprint` which: